ResEnsemble-DDPM: Residual Denoising Diffusion Probabilistic Models for Ensemble Learning
This work addresses image segmentation for computer vision applications, but it is incremental as it builds on existing models rather than introducing a new paradigm.
The paper tackled the problem of improving image segmentation performance by integrating denoising diffusion probabilistic models with existing end-to-end models through ensemble learning, resulting in enhanced capabilities and generalization to other tasks like image generation with strong competitiveness.
Nowadays, denoising diffusion probabilistic models have been adapted for many image segmentation tasks. However, existing end-to-end models have already demonstrated remarkable capabilities. Rather than using denoising diffusion probabilistic models alone, integrating the abilities of both denoising diffusion probabilistic models and existing end-to-end models can better improve the performance of image segmentation. Based on this, we implicitly introduce residual term into the diffusion process and propose ResEnsemble-DDPM, which seamlessly integrates the diffusion model and the end-to-end model through ensemble learning. The output distributions of these two models are strictly symmetric with respect to the ground truth distribution, allowing us to integrate the two models by reducing the residual term. Experimental results demonstrate that our ResEnsemble-DDPM can further improve the capabilities of existing models. Furthermore, its ensemble learning strategy can be generalized to other downstream tasks in image generation and get strong competitiveness.